SecurityNotebookcheckabout 1 hour ago
OpenAI patches ChatGPT chat leak flaw
3 min read
Security firm Parameter reported a ChatGPT flaw on October 18 that allowed strangers to read private chats via shared links. OpenAI raised the severity to P1 and paid a $5,000 bounty before fixing the issue on October 26. The vulnerability stemmed from a third-party library, MathLive, which accepted unverified HTML code from external sources.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
